state: generation 16787 (cycle)

.modelhub_state/architecture_compatibility_blacklist.json

@@ -3261,7 +3261,7 @@
       "taskType": "text-generation"
     }
   },
-  "generatedAt": "2026-09-26T20:19:50.860098+00:00",
+  "generatedAt": "2026-09-26T20:25:43.996253+00:00",
   "summary": {
     "activeBlockCount": 164,
     "byGpuFramework": {

.modelhub_state/market_intelligence.json

@@ -396,7 +396,7 @@
     }
   },
   "frameworkUpdatedAt": null,
-  "generatedAt": "2026-09-26T20:24:41.383836+00:00",
+  "generatedAt": "2026-09-26T20:26:24.552495+00:00",
   "gpuStats": {
     "Ascend_910-b4": {
       "available": true,

.modelhub_state/official_capabilities.json

@@ -1,5 +1,5 @@
 {
-  "catalogUpdatedAt": "2026-09-26T20:24:41.383836+00:00",
+  "catalogUpdatedAt": "2026-09-26T20:26:24.552495+00:00",
   "configuredTaskTypes": [
     "text-generation"
   ],
@@ -56,7 +56,7 @@
     "time-series-forecasting"
   ],
   "errors": [],
-  "generatedAt": "2026-09-26T20:24:41.383836+00:00",
+  "generatedAt": "2026-09-26T20:26:24.552495+00:00",
   "gpuCatalog": {
     "Ascend_910-b3": {
       "canVerify": true,
@@ -6265,6 +6265,6 @@
       "updateTime": "2025-12-22 08:59:53"
     }
   ],
-  "taskTreeUpdatedAt": "2026-09-26T20:24:41.383836+00:00",
+  "taskTreeUpdatedAt": "2026-09-26T20:26:24.552495+00:00",
   "version": 1
 }

.modelhub_state/outcome_checkpoint.json

@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-09-26T19:06:57.386426+00:00",
+  "generatedAt": "2026-09-26T20:25:43.917474+00:00",
-  "lastSyncTime": "2026-09-26T19:06:57.060378+00:00",
+  "lastSyncTime": "2026-09-26T20:25:43.664889+00:00",
   "recentLimit": 300,
   "report": {
     "architectureCompatibilityBlocks": {
@@ -3845,24 +3845,24 @@
         "decisionSuccessRate": 0.3636,
         "decisionTotal": 22,
         "failureBreakdown": {
-          "ambiguous_runtime": 37,
+          "ambiguous_runtime": 38,
           "framework_architecture_unsupported": 11,
           "model_load": 3,
           "platform_infrastructure": 1,
           "验证失败": 3
         },
-        "failureCount": 55,
+        "failureCount": 56,
-        "failureRate": 0.873,
+        "failureRate": 0.875,
         "framework": "vllm-mlu",
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 1,
         "successCount": 8,
-        "successRate": 0.127,
+        "successRate": 0.125,
         "targetGpu": "Cambricon_mlu-370-x4",
         "taskType": "text-generation",
-        "total": 63,
+        "total": 64,
-        "unresolvedFailureCount": 40
+        "unresolvedFailureCount": 41
       },
       "Cambricon_mlu-370-x4|vllm|text-generation": {
         "attributableFailureCount": 24,
@@ -6014,7 +6014,7 @@
         "decisionSuccessRate": 0.4167,
         "decisionTotal": 48,
         "failureBreakdown": {
-          "ambiguous_runtime": 84,
+          "ambiguous_runtime": 85,
           "framework_architecture_unsupported": 22,
           "model_load": 5,
           "platform_infrastructure": 1,
@@ -6022,15 +6022,15 @@
           "参数/模板问题": 3,
           "验证失败": 3
         },
-        "failureCount": 119,
+        "failureCount": 120,
-        "failureRate": 0.8561,
+        "failureRate": 0.8571,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 1,
         "successCount": 20,
-        "successRate": 0.1439,
+        "successRate": 0.1429,
-        "total": 139,
+        "total": 140,
-        "unresolvedFailureCount": 90
+        "unresolvedFailureCount": 91
       },
       "vllm-patch-tokenizer": {
         "attributableFailureCount": 55,
@@ -6133,7 +6133,7 @@
         "unresolvedFailureCount": 196
       }
     },
-    "generatedAt": "2026-09-26T19:06:57.373871+00:00",
+    "generatedAt": "2026-09-26T20:25:43.905349+00:00",
     "gpuSummaries": {
       "Ascend_910-b3": {
         "attributableFailureCount": 102,
@@ -6225,7 +6225,7 @@
         "decisionSuccessRate": 0.0894,
         "decisionTotal": 817,
         "failureBreakdown": {
-          "ambiguous_runtime": 488,
+          "ambiguous_runtime": 489,
           "architecture_compatibility": 53,
           "context_length": 48,
           "framework_architecture_unsupported": 297,
@@ -6238,15 +6238,15 @@
           "日志缺失": 13,
           "验证失败": 42
         },
-        "failureCount": 1589,
+        "failureCount": 1590,
         "failureRate": 0.9561,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 16,
         "successCount": 73,
         "successRate": 0.0439,
-        "total": 1662,
+        "total": 1663,
-        "unresolvedFailureCount": 829
+        "unresolvedFailureCount": 830
       },
       "Cambricon_mlu-370-x8": {
         "attributableFailureCount": 60,
@@ -10696,9 +10696,9 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "ambiguous_runtime": 7
+          "ambiguous_runtime": 8
         },
-        "failureCount": 7,
+        "failureCount": 8,
         "failureRate": 1.0,
         "framework": "vllm-mlu",
         "modelType": "llama",
@@ -10710,8 +10710,8 @@
         "successRate": 0.0,
         "targetGpu": "Cambricon_mlu-370-x4",
         "taskType": "text-generation",
-        "total": 7,
+        "total": 8,
-        "unresolvedFailureCount": 7
+        "unresolvedFailureCount": 8
       },
       "Cambricon_mlu-370-x4|vllm-mlu|text-generation|llama|none": {
         "attributableFailureCount": 0,
@@ -32952,9 +32952,9 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "ambiguous_runtime": 2
+          "ambiguous_runtime": 3
         },
-        "failureCount": 2,
+        "failureCount": 3,
         "failureRate": 1.0,
         "framework": "vllm-mlu",
         "loadSizeLog2Bucket": 30,
@@ -32967,8 +32967,8 @@
         "successRate": 0.0,
         "targetGpu": "Cambricon_mlu-370-x4",
         "taskType": "text-generation",
-        "total": 2,
+        "total": 3,
-        "unresolvedFailureCount": 2
+        "unresolvedFailureCount": 3
       },
       "Cambricon_mlu-370-x4|vllm-mlu|text-generation|llama|compressed-tensors|33": {
         "attributableFailureCount": 0,
@@ -50930,15 +50930,15 @@
         "unresolvedFailureCount": 0
       }
     },
-    "terminalRecords": 17046,
+    "terminalRecords": 17047,
-    "totalRecords": 17267,
+    "totalRecords": 17268,
     "totals": {
       "attributableFailureCount": 6114,
       "decisionFailureRate": 0.8636,
       "decisionSuccessRate": 0.1364,
       "decisionTotal": 7080,
       "failureBreakdown": {
-        "ambiguous_runtime": 4407,
+        "ambiguous_runtime": 4408,
         "architecture_compatibility": 212,
         "attention_backend": 3,
         "backend_operator": 128,
@@ -50954,30 +50954,30 @@
         "日志缺失": 719,
         "验证失败": 676
       },
-      "failureCount": 16080,
+      "failureCount": 16081,
       "failureRate": 0.9433,
       "pendingCount": 0,
       "pendingRate": 0.0,
       "platformFailureCount": 937,
       "successCount": 966,
       "successRate": 0.0567,
-      "total": 17046,
+      "total": 17047,
-      "unresolvedFailureCount": 9029
+      "unresolvedFailureCount": 9030
     },
     "warnings": [
       "GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
-      "GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
+      "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。",
-      "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
+      "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
-      "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
+      "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
-      "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
+      "GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
       "组合 Iluvatar_bi-150|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Sunrise_pt-200-x1|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -50990,7 +50990,6 @@
       "组合 Iluvatar_bi-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Cambricon_mlu-370-x4|vllm-mlu|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
-      "组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 hygon_k100-ai|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Ascend_910-b4|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Cambricon_mlu-370-x8|vllm-customized|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -51016,10 +51015,11 @@
       "组合 Cambricon_mlu-370-x4|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Ascend_910-b4|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
+      "组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 MetaX_c-500|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
     ]
   },
   "storageMode": "decision_state_only",
-  "summarizedRecords": 17267,
+  "summarizedRecords": 17268,
   "version": 1
 }

manifest.json

@@ -2,24 +2,24 @@
   "agentVersion": "2026.09.22.1",
   "checksums": {
     ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
-    ".modelhub_state/architecture_compatibility_blacklist.json": "b8bf5909df47ceb05afda596e494ffe35d5cd61b5c55aaf07696578d055041fe",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "2cc5dbccf168df4e8fae55eb78559766daaca2a642ed0e164641c3d5d93afdfc",
     ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
-    ".modelhub_state/market_intelligence.json": "a10addbfc55f15b94d75d683b009b03738b4c7e31e1ae67fce549894a67cf613",
+    ".modelhub_state/market_intelligence.json": "95a58597a6641f2c475cbd16c5d001170352acd2185f6143f7eaa076d9c0fcf2",
-    ".modelhub_state/official_capabilities.json": "51d19836973a640c9d420aa8edd2c0aed2415a6974fa7aeeba31bf63b45a7853",
+    ".modelhub_state/official_capabilities.json": "a002faac374539a48b02c2eccb4e7b1970e9354435c1bcd1550d65da033c782a",
-    ".modelhub_state/outcome_checkpoint.json": "d6801957f173b3cb12b824544113465b8ff4645d97a5bcc002ef26154b072ec1",
+    ".modelhub_state/outcome_checkpoint.json": "bf65ecf6939ac6f4af609113af4bbeff162c191b7e4543505ecb0c8dc777c668",
     ".modelhub_state/queue_cleanup_latest.json": "69b07b4c7f0e1a61310077a9b0cf5b45c959484d402ad60f0304381993afe5e7",
     ".modelhub_state/recent_outcomes.jsonl": "fc824b550dd2cad27bf01dd347e6709336ab8153748ad6b4ef4b0591070dd1dc",
-    ".modelhub_state/recovery_active_tasks.jsonl": "a0c034c644366a8b6a08afc0a3668a3f1b903cecf38388deaea6da7f89e66c90",
+    ".modelhub_state/recovery_active_tasks.jsonl": "1a4155d9ba9292179d57466b629dc3adf1fe0ec6fd6d3382ff7844c10624338a",
-    ".modelhub_state/recovery_intents.jsonl": "076c68c74c58afcd3981e2f473c5553db7c83b68b0b2da78db1bee36e4cc7acb",
+    ".modelhub_state/recovery_intents.jsonl": "0ba992ce4501bc5cb096f853ade122a092beb4e72753dedf949fc59fd6502f1c",
     ".modelhub_state/routing_intelligence.json": "519577e231ce3934d8378cbf1f13f1356f0576991f528675ded72ec2b8b3c804",
     ".modelhub_state/submission_exclusions.jsonl": "2cd0731cd4d31bc6d844f4f0a1e510e2fc839ca66f2ce07d2664110b33374799",
     ".modelhub_state/worker_crashes.jsonl": "ccd40ad86ab5068ea1c3520a48fa733cf2e4b357ae5abb95ff00728d5d1b5487",
     "ledger/submissions.jsonl": "6071510b13d7fa1186e155941f35e6810e50a687772bd3064a7286c5ba918d9c",
-    "outcomes/submissions.jsonl": "70bb72d511e35f530b62c67f4c42540f23ebf5b2a0a40de34ef6d494263cd8cb"
+    "outcomes/submissions.jsonl": "7930cbebe1be15cdba419d58431f6656ebbc39c6b1b27541580f0bd17e296048"
   },
-  "generation": 16786,
+  "generation": 16787,
   "phase": "cycle",
   "schemaVersion": 1,
-  "updatedAt": "2026-09-26T20:24:42.097568+00:00",
+  "updatedAt": "2026-09-26T20:26:27.529103+00:00",
   "writerId": "08206cb1993a433e83f1d3e297db2d2e"
 }

outcomes/submissions.jsonl

@@ -363,7 +363,6 @@
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:21:49.901746+00:00", "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 219850592, "estimatedRequiredGiB": 0.249, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 223236688, "modelscopeLicense": "apache-2.0", "modelscopeParams": 162826560, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 223236688}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:42.084586+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970594", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:21:49.901918+00:00", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 30797371689, "modelscopeLicense": "gemma", "modelscopeParams": 28406776320, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30797371689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:42.093442+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970600", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901870+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:15:36.946953+00:00", "targetGpu": "Vastai_va16", "taskId": "4970616", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T12:21:49.901693+00:00", "modelId": "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2024670536, "estimatedRequiredGiB": 2.273, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2033824831, "modelscopeLicense": "llama3.2", "modelscopeParams": 1498482688, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2033824831}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:19:00.650992+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970642", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:34:29.856383+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:26:45.109939+00:00", "targetGpu": "Vastai_va16", "taskId": "4970729", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T12:34:29.856278+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409935, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248409935}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:29:38.381652+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970762", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T12:34:29.856347+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:31:05.659043+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970789", "taskType": "text-generation", "verifyResult": null}